These tools and metrics are designed to help AI actors develop and use trustworthy AI systems and applications that respect human rights and are fair, transparent, explainable, robust, secure and safe.
Scope
SUBMIT A METRIC
If you have a tool that you think should be featured in the Catalogue of AI Tools & Metrics, we would love to hear from you!
Submit Equal performance 25 related use cases
If a model systematically makes errors disproportionately for patients in the protected group, it is likely to lead to unequal outcomes. Equal performance refers to the assurance that a model is equally accurate for patients in the protec...
Objectives:
Recall 9 related use cases
Recall is the fraction of the positive examples that were correctly labeled by the model as positive. It can be computed with the equation: Recall = TP / (TP + FN) Where TP is the number of true positives and FN is the number of false negatives.
Objectives:
Gender-based Illicit Proximity Estimate (GIPE) 5 related use cases
This paper proposes a new bias evaluation metric – Gender-based Illicit Proximity Estimate (GIPE), which measures the extent of undue proximity in word vectors resulting from the presence of gender-based predilections. Experiments based on a suite of...
Objectives:
Exact Match 2 related use cases
A given predicted string’s exact match score is 1 if it is the exact same as its reference string, and is 0 otherwise.
- Example 1: The exact match score of prediction “Happy Birthday!” is 0, given its reference is “Happy New Year!...
Objectives:
F-score 2 related use cases
In statistical analysis of binary classification, the F-score or F-measure is a measure of a test's accuracy. It is calculated from the precision and recall of the test, where the precision is the number of true positive results divided by the number of all...
Objectives:
Cross-lingual Natural Language Inference (XNLI) 1 related use case
The XNLI metric allows to evaluate a model’s score on the XNLI dataset, which is a subset of a few thousand examples from the MNLI dataset that have been translated into a 14 different languages, some of which are relatively low resource such as Swahili and...
Objectives:
Equality of Opportunity Difference (EOD) 1 related use case
We propose a criterion for discrimination against a specified sensitive attribute in supervised learning, where the goal is to predict some target based on available features. Assuming data about the predictor, target, and membership in the protected group...
Objectives:
Translation Edit Rate (TER) 1 related use case
Translation Edit Rate (TER), also called Translation Error Rate, is a metric to quantify the edit operations that a hypothesis requires to match a reference translation.
Objectives:
Statistical Parity Difference (SPD) 1 related use case
We study fairness in classification, where individuals are classified, e.g., admitted to a university, and the goal is to prevent discrimination against individuals based on their membership in some group, while maintaining utility for the classifier (the ...
Objectives:
Cross-lingual TRansfer Evaluation of Multilingual Encoders for Speech (XTREME-S)
XTREME-S can indirectly support the Fairness objective by providing a means to evaluate whether multilingual speech models perform equitably across different languages. By highlighting disparities in model performance for underrepr...
Objectives:
Spearman's rank correlation coefficient (SRCC)
In statistics, Spearman's rank correlation coefficient or Spearman's ρ is a non-parametric measure of rank correlation (statistical dependence between the rankings of two variables). It assesses how well the relationship between two variables can be describ...
Objectives:
Equal outcomes
In the field of health, equal patient outcomes refers to the assurance that protected groups have equal benefit in terms of patient outcomes from the deployment of machine-learning models. A weak form of equal outcomes is ensuring that both the protect...
Objectives:
False Rejection Rate (FRR)
False rejection rate (FRR) is a security metric used to measure the performance of biometric systems such as voice recognition, fingerprint recognition, face recognition, or iris recognition. It represents the likelihood of a biometric system mistakenly rej...
Objectives:
Cohen's Kappa coefficient
Cohen's kappa coefficient is a statistic that is used to measure inter-rater reliability (and also intra-rater reliability) for qualitative (categorical) items. It is generally thought to be a more robust measure than simple percent agreement calculation, a...
Objectives:
SAFE (Sustainable, Accurate, Fair and Explainable)
Machine learning models, at the core of AI applications, typically achieve a high accuracy at the expense of an insufficient explainability. Moreover, according to the proposed regulations, AI applications based on machine learning must be "trus...
Objectives:
Predictions Groups Contrast (PGC)
The PGC metric compares the top-K ranking of features importance drawn from the entire dataset with the top-K ranking induced from specific subgroups of predictions. It can be applied to both categorical and regression problems, being useful for quantifying...
Objectives:
Data Shapley
Objectives:
Data Banzhaf
Objectives:
Rank-Aware Divergence (RADio)
Objectives:
Conditional Demographic Disparity (CDD)
The demographic disparity metric (DD) determines whether a facet has a larger proportion of the rejected outcomes in the dataset than of the accepted outcomes. In the binary case where there are two facets, men and women for example, that constitute the dat...
Objectives:
